检查目标时出错:预期density_1具有4维,但数组的形状为(20,1)

时间:2019-04-11 03:24:48

标签: keras deep-learning

我正在尝试建立一个模型对我的图片进行分类(二进制),但是我遇到了这个问题,有人可以帮我解决这个问题。谢谢大家〜 这是模型,以及训练过程

def googLeNet(input = Input(shape=(224, 224, 3))):
    .................
    .................
    ...............
    averagepool1_7x7_s1 = AveragePooling2D(pool_size=(7, 7), padding='same')(inception_5b)
    drop1 = Dropout(rate=0.4)(averagepool1_7x7_s1)
    linear = Dense(units=1, activation='linear')(drop1)
    last = Dense(units=1, activation='softmax')(linear)
    model = Model(input=input, outputs=last)
    return model

-----------------------------------------------------------------------
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size=(224, 224),
    batch_size=20,
    class_mode='binary'
)

validation_generator = test_datagen.flow_from_directory(
    test_dir,
    target_size=(224, 224),
    batch_size=20,
    class_mode='binary'
)

model = googLeNet()
model.summary()
model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['acc']
              )

history = model.fit_generator(train_generator,
                              steps_per_epoch=100,
                              epochs=30,
                              validation_data=validation_generator,
                              validation_steps=50
                              )

0 个答案:

没有答案